Test: osd-recovery-space.sh extends the wait time for "recovery toofull".

The osd-recovery-space test involves writing objects and expecting to receive
the "toofull" flag.
If we don't wait long enough, we might check the "toofull" flag before all objects
have completed writing, and the "toofull" status hasn't been activated yet.

The change will extend the waiting time and will also incorporate additional
checks for the return code from the status wait.

Fixes: https://tracker.ceph.com/issues/44510
Signed-off-by: Nitzan Mordechai <nmordech@redhat.com>
(cherry picked from commit a7bd91dafb5736d2e3cae987e6164cdc14a0792a)

diff --git a/qa/standalone/osd/osd-recovery-space.sh b/qa/standalone/osd/osd-recovery-space.sh
index 3bafc5138bb328cdf2cb134730ee24b4f6f8f2b0..67fe2e91dfa2a07e87a7b985fb4f2e577a856d01 100755 (executable)
--- a/qa/standalone/osd/osd-recovery-space.sh
+++ b/qa/standalone/osd/osd-recovery-space.sh
@@ -76,6 +76,10 @@ function wait_for_state() {
 function wait_for_recovery_toofull() {
     local timeout=$1
     wait_for_state recovery_toofull $timeout
+    if [ $ret -ne 0 ]; then
+      echo "Error: Recovery toofull timeout"
+      return 1
+    fi
 }
 
 
@@ -131,7 +135,11 @@ function TEST_recovery_test_simple() {
     done
 
     # If this times out, we'll detected errors below
-    wait_for_recovery_toofull 30
+    wait_for_recovery_toofull 120
+    if [ $? -ne 0 ]; then
+      echo "Error: Recovery toofull timeout"
+      return 1
+    fi
 
     ERRORS=0
     if [ "$(ceph pg dump pgs | grep +recovery_toofull | wc -l)" != "1" ];